KR102385907B1 - Method And Apparatus for Autonomous Vehicle Navigation System - Google Patents

Abstract

In order to provide accurate autonomous vehicle navigation in a tunnel, the present invention receives an image of the front of the vehicle, converts the image in front of it into a binarization image, and the ratio of pixels having a brightness greater than or equal to a certain level in the binarization image. An area above a preset standard is extracted as a tunnel lighting candidate group, the tunnel lighting candidate group is converted into a vehicle center coordinate system, and the location of the vehicle is determined by map matching based on the converted tunnel lighting candidate group. It relates to a self-driving vehicle navigation device for determining and navigation thereof.

Description

Autonomous vehicle navigation system and navigation {Method And Apparatus for Autonomous Vehicle Navigation System}

The present invention relates to a navigation system for an autonomous vehicle, and more particularly, by detecting tunnel lighting in a tunnel and using it as an input value for map matching, using tunnel lighting that provides an accuracy solution in a tunnel to autonomous navigation technology It relates to an autonomous vehicle navigation system.

The existing autonomous driving navigation system has a disadvantage in that its performance and accuracy are poor in a special environment such as a tunnel. In particular, since the signal of the Global Positioning System (GPS) cannot be used in the tunnel section, a precise map matching technology is required to compensate for this. However, there have been limitations due to lane occlusion that may occur due to traffic congestion or loss of lanes due to contamination and lighting inside the tunnel.

In addition, the existing map matching using lanes has a disadvantage in that the accuracy of the longitudinal positioning is relatively lower than that of the lateral positioning due to the characteristics of the lane shape. In this case, as the length of the tunnel increases, there is a problem in that errors in the longitudinal direction are accumulated when driving using map matching.

An object of the present invention is to detect not only lanes but also tunnel lights from images obtained using the camera sensor of the embodiment and use them as input values for map matching, thereby solving the problem that the accuracy of the existing autonomous navigation technology decreases in the tunnel. The purpose is to suggest a way to solve it.

The problems of the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

According to an aspect of an embodiment of the present invention, the present invention includes a receiving unit for receiving a front image of a vehicle driving in a tunnel; a conversion unit converting the front image into a binarization image; an extracting unit for extracting, from the binarized image, an area in which a ratio of pixels having a brightness of a certain level or more is equal to or greater than a preset standard as a tunnel illumination candidate group; a coordinate system transformation unit converting the tunnel lighting candidate group into a vehicle center coordinate system; and

It includes an autonomous vehicle navigation device comprising a positioning unit that determines the location of the vehicle by map matching based on the converted tunnel lighting candidate group.

According to another aspect according to an embodiment of the present invention, the present invention includes a receiving process of receiving an image of the front of the vehicle; a binarization process of converting the front image into a binarization image; an extraction process of extracting, as a tunnel lighting candidate group, an area in the binarized image in which a ratio of pixels having a brightness equal to or greater than a predetermined threshold is greater than or equal to a preset standard; a coordinate transformation process of transforming the tunnel lighting candidate group into a vehicle center coordinate system; and a positioning process of determining the location of the vehicle by map matching based on the converted tunnel lighting candidate group.

According to the autonomous vehicle navigation system using the tunnel lighting of the present invention, there are one or more of the following effects.

First, it has the advantage of excellent positioning accuracy in the tunnel.

Second, there is also the advantage of being able to secure competitiveness as there is no additional cost and performance is improved.

Third, it is a vulnerable area for autonomous driving, such as a tunnel where GPS does not work when the vehicle is autonomously driving, and the vulnerability can be overcome by using tunnel lighting.

Fourth, compared to the existing autonomous driving method, there is an advantage in that the longitudinal accuracy of the tunnel is significantly improved.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

1 is a block diagram illustrating the configuration of an autonomous vehicle navigation device using tunnel lighting according to an embodiment of the present invention.
2 is a conceptual diagram illustrating a map matching technology of an autonomous vehicle navigation system using tunnel lighting according to an embodiment of the present invention.
3 is a block diagram illustrating a tunnel lighting detection technique for map matching according to an embodiment of the present invention.
4 is an exemplary diagram of autonomous driving using tunnel lighting according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout.

Hereinafter, the present invention will be described with reference to drawings for explaining an autonomous vehicle navigation system using tunnel lighting according to embodiments of the present invention.

1 is a block diagram showing the configuration of an autonomous vehicle navigation apparatus using tunnel lighting according to an embodiment of the present invention. Referring to FIG. 1 , an autonomous driving vehicle navigation apparatus using tunnel lighting according to an embodiment of the present invention includes a location information measurement unit 100 , an environment recognition sensor unit 200 , a radar sensing unit 300 , and sensor fusion positioning All or part of the unit 400 , the surrounding environment recognition unit 500 , the driving route generation unit 600 , and the vehicle control unit 700 are included.

The measuring part for positional information 100 measures the location information of the autonomous vehicle in real time. The location information measuring unit 100 may receive current location information and map information of the vehicle from a satellite. The location information measuring unit 100 may include a navigation system, a global navigation satellite system (GNSS), and the like.

The sensor part for environmental awareness 200 may capture images around the autonomous vehicle in real time. The environment recognition sensor unit 200 may include a lidar, a camera, a stereo camera, and the like.

The radar sensing part 300 outputs property and motion information of an object existing in an environment outside the vehicle. Through the analysis of radar information, information on external conditions such as the moving direction and speed of vehicles around the driving vehicle, traffic lights, pedestrians, and obstacles can be output. The radar detector 300 may include a vehicle to everything communication (V2X) terminal, a front radar, a rear radar, and the like.

A sensor convergence measuring unit (measuring part for sensor convergence) 400 determines the exact location of the vehicle through map matching technology based on the location information from the location information measurement unit 100 and the captured image from the environment recognition sensor unit 200 position can be estimated.

The part for surrounding awareness 500 may output surrounding environment information based on the captured image of the environment awareness sensor 200 and main information of the radar sensor 300 .

A part for generating driving route 600 may generate a route by combining output information from the sensor fusion positioning unit 400 and the surrounding environment recognition unit 500 .

A vehicle control unit (part for vehicle control) 700 may assist the autonomous driving of the vehicle based on the path generated by the driving path unit.

2 is a conceptual diagram illustrating a map matching technology of an autonomous vehicle navigation system using tunnel lighting according to an embodiment of the present invention.

FIG. 2A is an exemplary diagram of satellite positioning using the location information measuring unit 100 .

The location information measurement unit 100 may perform satellite positioning by utilizing sensors such as navigation and GNSS, and build a precision map 220 for sensor fusion of a currently driving vehicle based on the satellite positioning information.

2B is an exemplary diagram of lane extraction using the environment recognition sensor unit 200 .

The environmental awareness sensor unit 200 may extract the geometric structure 222 in front of the vehicle driving in the tunnel based on the rider.

The environment recognition sensor unit 200 extracts a lane 224 from an image taken based on an Advanced Driver Assistance System (ADAS) such as a Lane Keeping Assist System (LKAS) and a Lane Departure Warning System (LDWS) from the front image. can do.

FIG. 2(c) shows a map constructed in advance using a technology of statistical combination for positioning information and a sensor data matching technology and the estimated lanes are mutually matched ( 226), it is possible to estimate in advance the location 228 of the vehicle currently driving.

3 is a block diagram illustrating a tunnel lighting detection technique for map matching according to the present invention.

An image of the front of the vehicle is received from a camera mounted on the autonomous vehicle (S301).

The received front image is converted into a binarized image having a threshold value greater than or equal to a certain threshold. Among the converted binarized images, using a labeling technique, a portion having a certain size or more, a specific aspect ratio, and a ratio of bright pixels occupying the area of a certain level or more is determined as a tunnel illumination candidate group (S302).

Areas other than the tunnel lighting candidate group are determined as noise and removed (S303). The detected tunnel lighting candidate group is converted into a vehicle-centered coordinate system for map matching. For conversion, a conversion formula such as Equation 1 is applied (S304).

[Equation 1]

[Equation 2)

Here, u and v are values of the image coordinate system, and X, Y, and Z are values of the vehicle center coordinate system. s denotes a kind of scale factor of the homogenous coordinate system, M denotes intrinsic parameters of the camera, and r1 r2 r3 t denotes external parameters of the camera, respectively. h1 to h9 are parameters for moving from the image coordinate system to the vehicle-centered coordinate system, and can be calculated using at least four coordinate pairs of the image and the vehicle-centered coordinate system. At this time, the calculated height (Z) value of the tunnel lighting should be determined before the coordinate system transformation.

The converted lighting value is used in a map matching technique that identifies the location of an autonomous vehicle through matching with a pre-built map. Through the map matching technique, it is possible to fundamentally solve the problem of a decrease in detection accuracy due to lane contamination or traffic congestion, and it is very helpful in improving the performance of the positioning system for autonomous driving due to its fast processing speed and high accuracy can give

4 is an exemplary diagram of autonomous driving using tunnel lighting according to an embodiment of the present invention.

The map matching technique using the lane 410 has a limitation in that the lateral positioning is relatively accurate but the longitudinal positioning is less accurate due to the characteristic that the shape of the lane 410 is continuous in the longitudinal direction. . In particular, since GPS that transmits absolute positioning information cannot be used in the tunnel, the longitudinal error of map matching tends to accumulate. Therefore, by the time the vehicle passes through the tunnel, a longitudinal positioning error may occur from several tens of meters to more than 100 meters depending on the length of the tunnel. In the proposed patent, the central light 420 installed in the tunnel is used for map matching to solve the above fundamental problem. Specifically, this also stores the actual installation location (X, Y, Z) of the central light 420 on the map in advance, and coordinates transformation of the central light 420 detected using the front camera to map matching. method is carried out In this way, the accumulation of longitudinal errors can be prevented and the accuracy of the autonomous navigation system in the tunnel can be improved.

In the above, preferred embodiments of the present invention have been illustrated and described, but the present invention is not limited to the specific embodiments described above, and in the technical field to which the present invention belongs, without departing from the gist of the present invention as claimed in the claims Various modifications may be made by those of ordinary skill in the art, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

100: location information measurement unit
200: environment perception sensor unit
300: radar detection unit
400: sensor fusion positioning unit
500: surrounding environment recognition unit
600: driving route generation unit
700: vehicle control unit

Claims (9)

a receiving unit receiving an input of a front image of a vehicle driving in the tunnel;
a conversion unit converting the front image into a binarization image;
an extracting unit for extracting, from the binarized image, an area in which a ratio of pixels having a brightness of a certain level or more is equal to or greater than a preset standard as a tunnel illumination candidate group;
a coordinate system transformation unit converting the tunnel lighting candidate group into a vehicle center coordinate system; and
A positioning unit that determines the location of the vehicle by map matching based on the converted tunnel lighting candidate group,
The positioning unit,
Performing map matching on the location of the tunnel lighting stored in advance based on the converted tunnel lighting candidate group
Self-driving vehicle navigation system, characterized in that. The method of claim 1,
The extraction unit,
Among the binarized images, by labeling the binarized image, the tunnel illumination candidate group is extracted from a binarized image having a predetermined size or more and a constant horizontal to vertical ratio. 2. The method of claim 1
The coordinate system transformation unit,
The autonomous vehicle navigation device of claim 1, wherein the tunnel lighting candidate group is converted into the vehicle-centered coordinate system based on the height of the lighting in the tunnel. The method of claim 1,
The map matching is
The self-driving vehicle navigation device, characterized in that the operation is performed based on all or a part of the location information of the vehicle and an image captured around the vehicle. The method of claim 1,
The positioning unit,
and obtaining virtual lane information based on the tunnel lighting candidate group and surrounding environment information of the vehicle, and performing the map matching based on the virtual lane information. 6. The method of claim 5,
The virtual lane information is
An autonomous driving vehicle navigation device, characterized in that it is extracted based on ADAS (Advanced Driver Assistance Systems) using a vehicle front geometric structure extracted based on lidar. The method of claim 1,
The autonomous vehicle navigation apparatus of claim 1, further comprising: a driving path generator configured to generate a driving path of the vehicle based on the determined vehicle location and surrounding environment information of the vehicle. 8. The method of claim 7,
The autonomous driving vehicle navigation device according to claim 1, further comprising a vehicle controller configured to control the vehicle based on the generated driving route. A receiving process of receiving an image of the front of the vehicle;
a binarization process of converting the front image into a binarization image;
an extraction process of extracting, as a tunnel lighting candidate, an area in the binarized image in which a ratio of pixels having a brightness equal to or greater than a certain level is equal to or greater than a preset standard;
a coordinate transformation process of transforming the tunnel lighting candidate group into a vehicle center coordinate system; and
A positioning process of determining the location of the vehicle by map matching based on the converted tunnel lighting candidate group,
The positioning process is
Performing map matching on the location of the tunnel lighting stored in advance based on the converted tunnel lighting candidate group
Autonomous vehicle navigation characterized by

Images